TrajectoryDiversityforZero-ShotCoordinationAndreiLupu1BrandonCui2HengyuanHu2JakobFoerster2AbstractFigure1:Thecorridorcoordinationtaskadmitsthreeopti-malSPpolicies,onlyoneofwhichissuitableforZSC.Wes...
SolvingChallengingDexterousManipulationTasksWithTrajectoryOptimisationandReinforcementLearningHenryCharlesworth1GiovanniMontana1Abstractthehumanhand—capableoftasksrangingfromcomplexgraspingtowriti...
PrincipledSimplicialNeuralNetworksforTrajectoryPredictionT.MitchellRoddenberry1NicholasGlaze1SantiagoSegarra1Abstractintheirabilitytoincorporatearbitrarypairwiserelationalstructuresintheircomputati...
Large-ScaleMeta-LearningwithContinualTrajectoryShiftingJaeWoongShin1HaeBeomLee1BoqingGong21SungJuHwang13Abstractexamples(Lakeetal.,2015;Vinyalsetal.,2016;Santoroetal.,2016;Snelletal.,2017;Finnetal....
Self-ConsistentTrajectoryAutoencoder:HierarchicalReinforcementLearningwithTrajectoryEmbeddingsJohnD.Co-Reyes1YuXuanLiu1AbhishekGupta1BenjaminEysenbach2PieterAbbeel1SergeyLevine1Abstractinvolvetempo...
SpectralLearningfromaSingleTrajectoryunderFinite-StatePoliciesBorjaBalle1Odalric-AmbrymMaillard2Abstracting(estimated)momentsofthetargetdistribution(e.g.Hsuetal.(2012);Bootsetal.(2011);Balleetal.(2...